CN114202886B - Mine blasting safety monitoring and early warning system - Google Patents
Mine blasting safety monitoring and early warning system Download PDFInfo
- Publication number
- CN114202886B CN114202886B CN202111497572.1A CN202111497572A CN114202886B CN 114202886 B CN114202886 B CN 114202886B CN 202111497572 A CN202111497572 A CN 202111497572A CN 114202886 B CN114202886 B CN 114202886B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- unmanned aerial
- aerial vehicle
- video
- monitoring center
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 69
- 238000005422 blasting Methods 0.000 title claims abstract description 37
- 238000004891 communication Methods 0.000 claims description 25
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000005065 mining Methods 0.000 abstract description 10
- 239000003245 coal Substances 0.000 abstract description 2
- 238000007689 inspection Methods 0.000 description 14
- 238000000034 method Methods 0.000 description 9
- 238000013528 artificial neural network Methods 0.000 description 8
- 238000013527 convolutional neural network Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0205—Specific application combined with child monitoring using a transmitter-receiver system
- G08B21/0208—Combination with audio or video communication, e.g. combination with "baby phone" function
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0233—System arrangements with pre-alarms, e.g. when a first distance is exceeded
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0261—System arrangements wherein the object is to detect trespassing over a fixed physical boundary, e.g. the end of a garden
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/028—Communication between parent and child units via remote transmission means, e.g. satellite network
- G08B21/0283—Communication between parent and child units via remote transmission means, e.g. satellite network via a telephone network, e.g. cellular GSM
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
- H04N7/185—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source from a mobile camera, e.g. for remote control
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Child & Adolescent Psychology (AREA)
- Emergency Management (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Aviation & Aerospace Engineering (AREA)
- Signal Processing (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Emergency Alarm Devices (AREA)
- Alarm Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a mine blasting safety monitoring and early warning system, which comprises: the video monitoring unmanned aerial vehicle is used for carrying out video monitoring according to a preset flight line, the video monitoring unmanned aerial vehicle sends collected video data to the AI monitoring center through a 5G network, and the AI monitoring center analyzes pictures in a monitoring video through an AI algorithm and sends out alarm operation after identifying alarm information. The invention has the advantages that: the monitoring and early warning are realized through the unmanned aerial vehicle, so that the mining area in the blasting area is monitored, the safety is improved, and the safety accidents in the blasting area of the mining area are reduced; the unmanned aerial vehicle is used for dynamically inspecting the coal mine blasting area, so that the monitoring of real-time video can be remotely realized.
Description
Technical Field
The invention relates to the field of safety monitoring, in particular to a mine blasting safety monitoring and early warning system.
Background
The blasting construction site environment is complex, the conventional remote monitoring equipment and the manual management are difficult to realize dead angle-free safety supervision, the monitoring is more focused on individual key areas, and the real-time reporting of the construction site cannot be dynamically carried out in the whole process. The blasting operation needs to reasonably design the blasting warning range and carry out blasting safety warning, and the traditional warning mode is used for blocking surrounding roads, arranging warning points and pulling warning lines, and prohibiting passing.
However, in practice, when the blasting warning range is large, the terrain is complex, the visual field is narrow, and the surrounding traffic environment is complex, the blasting safety warning dispatching command system established by whistle, warning flag, interphone and the like often has loopholes, so that comprehensive monitoring and investigation cannot be realized, and meanwhile, the warning information is dispersed and not visual, so that danger is easily caused by warning blind areas. The blasting warning general command lacks macroscopic control on the warning state and effect, cannot intuitively acquire monitoring data, and is unfavorable for scientific and reasonable decision and blasting safety warning command.
In the prior art, unmanned aerial vehicle is high in shooting precision, fast in imaging, flexible in operation and the like, if the monitoring of a blasting area is combined with the unmanned aerial vehicle to realize remote dynamic monitoring, various data in the blasting area can be monitored rapidly, monitoring and scheduling are facilitated, and safety of the blasting area is improved.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a mine blasting safety monitoring and early warning system and method, which are used for realizing safety monitoring in a corresponding mine blasting area based on unmanned aerial vehicles and 5G communication technology.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: a mine blasting safety monitoring and early warning system, comprising: the video monitoring unmanned aerial vehicle is used for carrying out video monitoring according to a preset flight line, the video monitoring unmanned aerial vehicle sends collected video data to the AI monitoring center through a 5G network, and the AI monitoring center analyzes pictures in a monitoring video through an AI algorithm and sends out alarm operation after identifying alarm information.
The AI algorithm uses the yolov5 model. Is an object detection algorithm that segments an image into a grid system. Including determining where certain objects are present in the image and classifying those objects. Previous methods, such as R-CNN and its variants, use a pipeline to perform this task in multiple steps. This can be slow running and difficult to optimize because each individual component must be trained individually. YOLO can be solved with only one neural network, simply taking an image as input, and obtaining a vector containing bounding boxes and class predictions in the output through a neural network that looks like a normal CNN.
The monitoring unmanned aerial vehicle is built-in with camera and communication with 5G communication chip for the video acquisition, the video data that the camera gathered is connected with 5G communication base station communication through 5G communication chip, 5G communication base station sends real-time video stream data to AI monitoring center.
The video monitoring unmanned aerial vehicle supports remote control of a remote controller, and the remote controller controls a flight path according to a user remote control signal.
The AI monitoring center analyzes and identifies people and vehicles in the blasting area through an AI algorithm and sends out an alarm signal; the AI monitoring center analyzes and identifies people and vehicles in the video through an AI algorithm and marks the identified people and vehicles on a picture; and or the AI monitoring center is used for playing the video marked with the people and the vehicles in the identified people and vehicle information and the video data through a real-time picture.
And the AI monitoring center recognizes the information of the vehicles and the people through an AI algorithm and then gives an alarm, and the alarm module is integrated in the video monitoring unmanned aerial vehicle.
The control system of the unmanned aerial vehicle controls the playing of the shouting audio according to analysis, identification and combination fed back by the AI monitoring center and alarm information.
The unmanned aerial vehicle is built-in word voice conversion module for with self-defined megaphone characters conversion to pronunciation.
The monitoring and early warning system also comprises an AI reasoning platform, wherein the AI reasoning platform comprises an unmanned aerial vehicle device management module, an AI algorithm management and service scheduling module, an alarm rule setting module and an alarm log and algorithm log inquiring module. Each functional module of the AI reasoning platform:
1) Unmanned aerial vehicle equipment management module:
and the unmanned aerial vehicle is docked with an open platform, so that the unmanned aerial vehicle flight control and the flight information acquisition are realized.
2) AI algorithm and service scheduling module:
when the unmanned aerial vehicle flies, the rtsp flow of the unmanned aerial vehicle is taken in real time,
and (3) processing the rtsp stream in real time, converting the stream into image frames, and pushing the image frames to an AI reasoning service for analysis.
And writing the reasoning log and the early warning log into a database.
3) Alarm rule:
setting inference parameters such as classification and confidence level
4) Alarm log and algorithm log query module:
and according to the flight time of the unmanned aerial vehicle, reasoning, classifying, inquiring, alarming and algorithm journals.
The AI monitoring center comprises a cloud server, a local server and a monitoring center management configuration system, wherein the cloud server is respectively connected with the local server and the monitoring center management configuration system, and the low server displays monitoring data through a display screen.
And (3) a monitoring center:
1) Displaying the flight control state of the unmanned aerial vehicle on a large screen in real time, displaying position information on a map, and drawing a flight track. The flight path of the unmanned aerial vehicle can be set.
2) Real-time display unmanned plane shooting picture (infrared + visible light)
3) The large screen is realized by adopting html5, rtmp/hls, rest, websocket and other modes.
The self-defined megaphone text in the unmanned aerial vehicle is configured by the AI monitoring center and then transmitted to the control system of the unmanned aerial vehicle.
The invention has the advantages that: the monitoring and early warning are realized through the unmanned aerial vehicle, so that the mining area in the blasting area is monitored, the safety is improved, and the safety accidents in the blasting area of the mining area are reduced; the unmanned aerial vehicle is used for carrying out dynamic inspection on the coal mine blasting area, so that the monitoring of real-time video can be remotely realized; the 5G is adopted to transmit the real-time video data stream, so that the delay is less, the transmission is quick, and the real-time monitoring can be realized; the AI monitoring center server operates an AI algorithm to identify the people and vehicles in the inspection area, and the people and vehicles can be directly alarmed after being identified or monitored and displayed through a local monitoring large screen of the monitoring center; unmanned aerial vehicle supports the pronunciation function of shouting out, can long-range pronunciation shouting out to drive away.
Drawings
The contents of the drawings and the marks in the drawings of the present specification are briefly described as follows:
FIG. 1 is a deployment framework of the early warning system of the present invention.
Detailed Description
The following detailed description of the invention refers to the accompanying drawings, which illustrate preferred embodiments of the invention in further detail.
The invention utilizes the advantages of high shooting precision, quick imaging, flexible operation and the like of the unmanned aerial vehicle, and simultaneously utilizes the AI technology to intelligently identify and alarm the blasting guard zone, thereby realizing the safety supervision of blasting construction, improving the working efficiency and avoiding the occurrence of safety accidents. The specific scheme is as follows:
as shown in fig. 1, a mine blasting safety monitoring and early warning system includes: the system comprises a video monitoring unmanned aerial vehicle and an AI monitoring center, wherein the video monitoring unmanned aerial vehicle is used for carrying out video monitoring according to a preset flight line and collecting video data in a mining area on a flight path; the video monitoring unmanned aerial vehicle sends the collected video data to the AI monitoring center through a 5G network, and the data can be quickly and reliably sent to the AI monitoring center in a low-delay manner by adopting a 5G communication mode; the video monitoring unmanned aerial vehicle comprises an unmanned aerial vehicle, a camera module and a 5G communication chip, wherein the camera module is integrated on the unmanned aerial vehicle and used for video acquisition, the unmanned aerial vehicle is provided with an unmanned aerial vehicle control system, the unmanned aerial vehicle control system is respectively connected with the camera module and the 5G communication chip, and the unmanned aerial vehicle control system is used for controlling the flight path of the unmanned aerial vehicle, acquiring video data through the camera module and sending the data to an AI monitoring center for monitoring through the 5G communication chip by adopting a 5G network.
The monitoring unmanned aerial vehicle is built-in with camera and communication with 5G communication chip for video acquisition, the video data that the camera gathered is connected with 5G communication base station communication through 5G communication chip, 5G communication base station sends real-time video stream data to AI monitoring center.
The AI monitoring center receives video data sent by the 5G network, analyzes pictures in the monitoring video through an AI algorithm, recognizes alarm information and then sends out alarm operation. The identified alarm information is information of vehicles and people in the mining area, and the alarm operation comprises the steps of sending alarm signals, controlling the monitoring large screen to display the alarm information and controlling the monitoring large screen to mark the vehicles and the people in the video for display:
the AI monitoring center analyzes and identifies people and vehicles in the blasting area through an AI algorithm and sends out alarm signals, and can carry out image picture alarm through a display screen of the AI monitoring center or send out voice alarm through a voice module of the AI monitoring center;
the AI monitoring center comprises a server and a large monitoring screen, the server is used for realizing the analysis and processing of data by an AI algorithm, the large monitoring screen is used for sending out alarm picture information, the server of the AI monitoring center analyzes and identifies people and vehicles in videos through the AI algorithm and marks the identified people and vehicles on pictures, the videos of the vehicles and the people at the identification position are displayed through the large monitoring screen, so that the remote real-time picture monitoring is realized, and the server can be further connected with a voice alarm system to send out voice alarm signals; the AI monitoring center plays the identified person and car information and the video marked with the person and car in the video data through the real-time picture, and the purpose of real-time monitoring can be achieved because the received 5G video stream data is fast. The AI algorithm is integrated in the server for recognition analysis processing.
Furthermore, the AI monitoring center recognizes the information of the vehicles and the people through an AI algorithm and then gives an alarm, and the alarm module can be integrated in the video monitoring unmanned aerial vehicle. The control system output end of the unmanned aerial vehicle is connected with the alarm module, and the unmanned aerial vehicle control system controls the alarm module to send alarm signals in a driving control mode, such as alarm sound and the like. The audio of shouting is preset in the video monitoring unmanned aerial vehicle, and the control system of the unmanned aerial vehicle controls the playing of the audio of shouting according to analysis, identification and combination fed back by the AI monitoring center and alarm information. The alarm module adopts a voice module, the AI monitoring system analyzes the information of people and vehicles and then sends out alarm control signals to the unmanned aerial vehicle control system through the 5G network, the unmanned aerial vehicle control system receives the alarm control signals and then controls the alarm module to send out voice alarm, and the voice alarm module recognizes preset megaphone audio and then plays the audio so as to achieve the purpose of alarm. Custom megaphone characters in the unmanned aerial vehicle are configured by the AI monitoring center and then transmitted to a control system of the unmanned aerial vehicle. The shouting characters can be input by the peripheral equipment (man-machine interaction equipment) of the AI monitoring center and then transmitted to the unmanned aerial vehicle control system through the 5G network or input by the unmanned aerial vehicle remote controller and the like. Therefore, the self-definition of the shouting is realized, the identifiability of the content of the shouting is improved, and the communication and communication between the shouting and the personnel in the mining area can be realized and timely driving away can be realized.
The AI algorithm adopts a yolov5 model, and is a target detection algorithm for dividing an image into a grid system. Including determining where certain objects are present in the image and classifying those objects. Previous methods, such as R-CNN and its variants, use a pipeline to perform this task in multiple steps. This can be slow running and difficult to optimize because each individual component must be trained individually. YOLO can be solved with only one neural network, simply taking an image as input, you get a vector containing bounding boxes and class predictions in the output through a neural network that looks like a normal CNN.
In the application, the flight path of the unmanned aerial vehicle can be remotely controlled through a remote controller, the video monitoring unmanned aerial vehicle supports remote control of the remote controller, and the flight area and the flight path of the unmanned aerial vehicle are controlled through manual remote control of the remote controller or preset through the remote controller.
The monitoring and early warning system also comprises an AI reasoning platform, wherein the AI reasoning platform comprises an unmanned aerial vehicle device management module, an AI algorithm management and service scheduling module, an alarm rule setting module and an alarm log and algorithm log inquiring module. The AI reasoning platform includes:
1) Unmanned aerial vehicle equipment management module:
and the unmanned aerial vehicle is docked with an open platform, so that the unmanned aerial vehicle flight control and the flight information acquisition are realized.
2) AI algorithm and service scheduling module:
when the unmanned aerial vehicle flies, the rtsp flow of the unmanned aerial vehicle is taken in real time,
and (3) processing the rtsp stream in real time, converting the stream into image frames, and pushing the image frames to an AI reasoning service for analysis.
And writing the reasoning log and the early warning log into a database.
3) Alarm rule:
setting inference parameters such as classification and confidence level
4) Alarm log and algorithm log query module:
and according to the flight time of the unmanned aerial vehicle, reasoning, classifying, inquiring, alarming and algorithm journals.
The unmanned aerial vehicle management module is used for managing and configuring a system of the unmanned aerial vehicle, and can remotely set configuration, operation route and the like of the unmanned aerial vehicle.
The AI monitoring center comprises a cloud server, a local server and a monitoring center management configuration system, wherein the cloud server is respectively connected with the local server and the monitoring center management configuration system, and the local server displays monitoring data through a display screen.
And (3) a monitoring center:
1) Displaying the flight control state of the unmanned aerial vehicle on a large screen in real time, displaying position information on a map, and drawing a flight track. The flight path of the unmanned aerial vehicle can be set.
2) Real-time display unmanned plane shooting picture (infrared + visible light)
3) The large screen is realized by adopting html5, rtmp/hls, rest, websocket and other modes.
The method is characterized by the integration of 5G+AI:
(1) Supporting 5G network connection, and realizing high-bandwidth and low-delay unmanned aerial vehicle network video live broadcast;
(2) And the autonomous AI recognition scheme is optimized by a customized algorithm, so that unmanned aerial vehicle mine inspection high definition and efficient AI analysis and landing are realized.
The AI algorithm detects moving objects such as personnel, vehicles and the like, the unmanned aerial vehicle carries out regional patrol according to a set track, the AI algorithm carries out automatic detection on a video transmitted back in real time, an alarm is detected as a target, and alarm information is displayed on a locally deployed algorithm demonstration platform.
AI monitoring center:
based on the professional unmanned aerial vehicle platform, customized development and AI analysis can realize the following scenes:
performing a patrol/blasting task: the unmanned aerial vehicle takes off and carries out mining area safety monitoring;
(1) AI algorithm analysis: the mining area personnel and vehicle inspection, personnel and vehicle identification, personnel and vehicle early warning in the blasting area, and the blasting warning area is defined, and personnel and vehicles are detected and warned in the area;
the AI algorithm uses the yolov5 model. Is an object detection algorithm that segments an image into a grid system. Including determining where certain objects are present in the image and classifying those objects. Previous methods, such as R-CNN and its variants, use a pipeline to perform this task in multiple steps. This can be slow running and difficult to optimize because each individual component must be trained individually. YOLO, can be solved with only one neural network,
briefly, taking an image as an input, you get a vector that contains bounding boxes and class predictions in the output, through a neural network that looks like a normal CNN.
The principle is as follows:
(2) Monitoring center real-time picture: displaying a real-time picture of the unmanned aerial vehicle, and marking the information of people and vehicles in the picture;
(3) Real-time early warning of the monitoring center: discovering a man-car, and discovering the man-car in a blasting area;
(4) Unmanned aerial vehicle shouting: the unmanned aerial vehicle presets the audio of shouting, reminds workman and vehicle to avoid danger in time. (some models support custom shouting content, support text to speech, etc.)
AI reasoning platform:
the AI reasoning platform is an important management system for supporting the unmanned aerial vehicle intelligent inspection landing, ensures the normal operation of each function of the system by the high-availability system architecture, and comprises the following functions:
(1) Managing unmanned aerial vehicle equipment;
the unmanned aerial vehicle cloud open platform is docked, and unmanned aerial vehicle flight control and flight information acquisition are achieved, wherein unmanned aerial vehicle state, position and other information acquisition are achieved.
(2) AI algorithm management and service scheduling;
when the unmanned aerial vehicle flies, the rtsp flow of the unmanned aerial vehicle is taken in real time,
and (3) processing the rtsp stream in real time, converting the stream into image frames, and pushing the image frames to an AI reasoning service for analysis.
And writing the reasoning log and the early warning log into a database.
(3) Alarm rule setting:
setting inference parameters such as classification and confidence level
(4) Inquiring an alarm log and an algorithm log;
and according to the flight time of the unmanned aerial vehicle, reasoning, classifying, inquiring, alarming and algorithm journals.
Unmanned aerial vehicle mine solution with 5g+ai features is intended to solve the following pain point problems:
1) The manual inspection efficiency is low: the manual inspection is difficult and low in efficiency in places such as mines and tailing areas, and the problems of inconvenience in night inspection and the like exist.
2) Full-field monitoring is not possible: the traditional inspection efficiency is low, the probability of the inspection area re-danger is improved, and the inspection area re-danger cannot be monitored in time.
3) The risk of the explosion area is high: the blasting operation on the mine is conventional operation, but the inspection danger of the related area is high and the difficulty is high.
4) The system linkage is low: cannot monitor or link with other systems such as mining management, remote blasting and the like, and cannot achieve higher safety linkage and inspection record inquiry.
The AI reasoning platform is an important management system for supporting the unmanned aerial vehicle intelligent inspection landing, and ensures that each function of the system operates normally by the high-availability system architecture:
(1) High availability architecture: adopting a containerization technology to quickly fall to the ground; adopting K8S to carry out clustering management, and ensuring the availability of the system;
(2) High-efficiency algorithm training: professional algorithm full training and landing scheme, and the most rapid 3-hour algorithm landing record of similar scenes;
(3) Customizing the camera layout: establishing files for each camera point position, and setting exclusive camera angle, polishing, definition, focal length and other construction schemes;
(4) High availability AI central management system: and uniformly scheduling unmanned aerial vehicle, cameras and AI algorithm, pushing AI analysis results in real time, displaying the AI analysis results on a large screen of the terminal, and stabilizing the output of the analysis results within 2 s.
(5) Efficient algorithm training: the AI algorithm uses the yolov5 model. Is an object detection algorithm that segments an image into a grid system. Including determining where certain objects are present in the image and classifying those objects. Previous methods, such as R-CNN and its variants, use a pipeline to perform this task in multiple steps. This can be slow running and difficult to optimize because each individual component must be trained individually. YOLO, can be solved with only one neural network,
briefly, taking an image as an input, you get a vector that contains bounding boxes and class predictions in the output, through a neural network that looks like a normal CNN.
The method has the design rules (input, width and depth) similar to the EfficientNet network, and the matching strategy of the cross-neighborhood grid, can be quickly converged on a plurality of data sets, and has strong model customization.
(6) Algorithm deployment: localization training and cloud server reasoning. And (3) carrying out localized model training according to the actual scene by the senior algorithm engineer, and uploading the model to a cloud for system reasoning after obtaining the model.
It is obvious that the specific implementation of the present invention is not limited by the above-mentioned modes, and that it is within the scope of protection of the present invention only to adopt various insubstantial modifications made by the method conception and technical scheme of the present invention.
Claims (1)
1. The utility model provides a mine blasting safety monitoring early warning system which characterized in that: comprising the following steps: the system comprises a video monitoring unmanned aerial vehicle and an AI monitoring center, wherein the video monitoring unmanned aerial vehicle is used for carrying out video monitoring according to a preset flight line, the video monitoring unmanned aerial vehicle sends collected video data to the AI monitoring center through a 5G network, and the AI monitoring center analyzes pictures in a monitoring video through an AI algorithm and sends out alarm operation after identifying alarm information; the monitoring unmanned aerial vehicle is internally provided with a camera for video acquisition and a 5G communication chip for communication, video data acquired by the camera are in communication connection with a 5G communication base station through the 5G communication chip, and the 5G communication base station sends real-time video stream data to an AI monitoring center; the video monitoring unmanned aerial vehicle supports remote control of a remote controller, and the remote controller controls a flight path according to a user remote control signal; the AI monitoring center analyzes and identifies people and vehicles in the blasting area through an AI algorithm and sends out an alarm signal; the AI monitoring center analyzes and identifies people and vehicles in the video through an AI algorithm and marks the identified people and vehicles on a picture; the AI monitoring center is used for playing the video marked with the people and the vehicles in the identified people and the vehicle information and the video data through a real-time picture; the AI monitoring center recognizes the information of the vehicles and the persons through an AI algorithm and then gives an alarm, and the alarm module is integrated in the video monitoring unmanned aerial vehicle; the control system of the unmanned aerial vehicle controls the playing of the shouting audio according to analysis, identification and combination fed back by the AI monitoring center and alarm information; the unmanned aerial vehicle is internally provided with a text-to-speech conversion module which is used for converting custom shouting characters into speech; the monitoring and early warning system also comprises an AI reasoning platform, wherein the AI reasoning platform comprises an unmanned aerial vehicle equipment management module, an AI algorithm management and service scheduling module, an alarm rule setting module and an alarm log and algorithm log inquiring module; the AI monitoring center comprises a cloud server, a local server and a monitoring center management configuration system, wherein the cloud server is respectively connected with the local server and the monitoring center management configuration system, and the local server displays monitoring data through a display screen; the self-defined megaphone characters in the unmanned aerial vehicle are configured by the AI monitoring center and then transmitted to a control system of the unmanned aerial vehicle;
the AI monitoring center is configured to:
displaying the flight control state of the unmanned aerial vehicle on a large screen in real time, displaying position information on a map, and drawing a flight track; the flight track of the unmanned aerial vehicle can be set;
displaying pictures shot by the unmanned aerial vehicle on a large screen in real time, and playing the identified person and vehicle information and video marked with the person and vehicle in the video data through the real-time pictures by the AI monitoring center;
the large screen is realized by adopting an html5, rtmp/hls, rest or websocket mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111497572.1A CN114202886B (en) | 2021-12-09 | 2021-12-09 | Mine blasting safety monitoring and early warning system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111497572.1A CN114202886B (en) | 2021-12-09 | 2021-12-09 | Mine blasting safety monitoring and early warning system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114202886A CN114202886A (en) | 2022-03-18 |
CN114202886B true CN114202886B (en) | 2024-02-23 |
Family
ID=80651565
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111497572.1A Active CN114202886B (en) | 2021-12-09 | 2021-12-09 | Mine blasting safety monitoring and early warning system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114202886B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116030391B (en) * | 2023-01-06 | 2023-07-21 | 滨州邦维信息科技有限公司 | Intelligent monitoring method for personnel risk of coal discharge port |
CN117196408B (en) * | 2023-10-12 | 2024-03-22 | 西南水泥有限公司 | Mine safety wisdom monitoring system based on big data |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105915845A (en) * | 2016-04-25 | 2016-08-31 | 广东振声科技股份有限公司 | Blasting site unmanned aerial vehicle monitoring control method |
CN107757939A (en) * | 2017-09-29 | 2018-03-06 | 贵州安凯达实业股份有限公司 | A kind of blast working on-the-spot make an inspection tour device |
CN109905675A (en) * | 2019-03-13 | 2019-06-18 | 武汉大学 | A kind of mine personnel monitoring system based on computer vision and method |
CN109922309A (en) * | 2019-01-04 | 2019-06-21 | 浙江海洋大学 | A kind of engineering explosion operation field emergency management and rescue resource information management system |
CN110155326A (en) * | 2019-05-15 | 2019-08-23 | 湖南优加特装智能科技有限公司 | A kind of gridding security protection intelligent patrol system and control method based on unmanned plane |
WO2020062178A1 (en) * | 2018-09-29 | 2020-04-02 | 深圳市大疆创新科技有限公司 | Map-based method for identifying target object, and control terminal |
CN111238323A (en) * | 2020-03-09 | 2020-06-05 | 深圳市宏源建设工程有限公司 | Remote monitoring system for controlling blasting |
CN112423124A (en) * | 2020-11-20 | 2021-02-26 | 广州欢网科技有限责任公司 | Dynamic playing method, device and system based on large-screen video player |
CN112629346A (en) * | 2020-11-27 | 2021-04-09 | 杭州晋旗电子科技有限公司 | Safe initiation method for electronic detonator |
CN113235468A (en) * | 2021-05-14 | 2021-08-10 | 哈尔滨昊宸建研科技有限公司 | Large bridge blasting demolition monitoring system and application method thereof |
CN113556508A (en) * | 2021-05-11 | 2021-10-26 | 华洋通信科技股份有限公司 | Underground intelligent identification system for mine |
-
2021
- 2021-12-09 CN CN202111497572.1A patent/CN114202886B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105915845A (en) * | 2016-04-25 | 2016-08-31 | 广东振声科技股份有限公司 | Blasting site unmanned aerial vehicle monitoring control method |
CN107757939A (en) * | 2017-09-29 | 2018-03-06 | 贵州安凯达实业股份有限公司 | A kind of blast working on-the-spot make an inspection tour device |
WO2020062178A1 (en) * | 2018-09-29 | 2020-04-02 | 深圳市大疆创新科技有限公司 | Map-based method for identifying target object, and control terminal |
CN109922309A (en) * | 2019-01-04 | 2019-06-21 | 浙江海洋大学 | A kind of engineering explosion operation field emergency management and rescue resource information management system |
CN109905675A (en) * | 2019-03-13 | 2019-06-18 | 武汉大学 | A kind of mine personnel monitoring system based on computer vision and method |
CN110155326A (en) * | 2019-05-15 | 2019-08-23 | 湖南优加特装智能科技有限公司 | A kind of gridding security protection intelligent patrol system and control method based on unmanned plane |
CN111238323A (en) * | 2020-03-09 | 2020-06-05 | 深圳市宏源建设工程有限公司 | Remote monitoring system for controlling blasting |
CN112423124A (en) * | 2020-11-20 | 2021-02-26 | 广州欢网科技有限责任公司 | Dynamic playing method, device and system based on large-screen video player |
CN112629346A (en) * | 2020-11-27 | 2021-04-09 | 杭州晋旗电子科技有限公司 | Safe initiation method for electronic detonator |
CN113556508A (en) * | 2021-05-11 | 2021-10-26 | 华洋通信科技股份有限公司 | Underground intelligent identification system for mine |
CN113235468A (en) * | 2021-05-14 | 2021-08-10 | 哈尔滨昊宸建研科技有限公司 | Large bridge blasting demolition monitoring system and application method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN114202886A (en) | 2022-03-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114202886B (en) | Mine blasting safety monitoring and early warning system | |
WO2020113660A1 (en) | Patrol robot and patrol robot management system | |
CN108922188B (en) | Radar tracking and positioning four-dimensional live-action traffic road condition perception early warning monitoring management system | |
EP3459812A1 (en) | Detection system for a vehicle | |
US20070291985A1 (en) | Intelligent railyard monitoring system | |
KR102208152B1 (en) | System and method for response disaster situations in mountain area using UAS | |
CN203870474U (en) | Automatic navigation patrol robot for visual monitoring | |
US11995999B2 (en) | Drone first responder assistance | |
CN201846437U (en) | High-definition video monitoring system for truck loading state | |
CN106205042A (en) | Subway crowded trampling accident early warning linkage system and early warning linkage method | |
KR102161917B1 (en) | Information Processing System and method for rescue in mountain area using UAS | |
CN114394100B (en) | Unmanned patrol car control system and unmanned car | |
KR102166432B1 (en) | Method for replying disaster situation using smart drone | |
CN111102967A (en) | Intelligent navigation mark supervision system and method based on unmanned aerial vehicle | |
CN111696390A (en) | Intelligent airport runway FOD device and working process thereof | |
CN203465850U (en) | Artificial intelligence driving safety warning system | |
CN118397794A (en) | Intelligent sensing and early warning method and system for man falling into water | |
CN105760853A (en) | Personnel flow monitoring unmanned aerial vehicle | |
US11482124B2 (en) | Aerospace hazard detection, recognition, prioritization and warning device, system and associated methods | |
CN117649741A (en) | Real-time monitoring system and method for high-risk animals around transformer substation based on deep learning | |
CN116580558A (en) | Multifunctional traffic guideboard | |
US12043420B2 (en) | Drone, drone docking port and method of use | |
KR102538548B1 (en) | System for recognizing and monitoring object based on deep learning | |
CN114663818A (en) | Airport operation core area monitoring and early warning system and method based on vision self-supervision learning | |
KR102648144B1 (en) | Smart traffic light guidance system for crosswalks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |